remsky
d50214d3be
Enable ONNX GPU support in Docker configurations and refactor model file handling
2025-01-22 05:00:38 -07:00
remsky
4a24be1605
Refactor model loading and configuration: update, adjust model loading device,. add async streaming examples and remove unused warmup service.
2025-01-22 02:33:29 -07:00
remsky
21bf810f97
Enhance model inference: update documentation, add model download scripts for PyTorch and ONNX, and refactor configuration handling
2025-01-21 21:44:21 -07:00
Fireblade
53c8c9ca5d
Fixed thread leak because of creating excessive E-speak backends
2025-01-21 14:45:43 -05:00
remsky
ab28a62e86
Refactor inference architecture: remove legacy TTS model, add ONNX and PyTorch backends, and introduce model configuration schemas
2025-01-20 22:42:29 -07:00
Richard Roberson
d51d861861
add AAC audio format and test
2025-01-17 21:43:10 -07:00
Fireblade2534
eb556ec7d3
Fixed python tests so they run properly and cleaned up some unneeded files
2025-01-17 14:55:25 +00:00
remsky
d20da2f92e
Default hexxgrad voicepacks added as temporary fix
2025-01-15 09:42:27 +00:00
remsky
8bc8661930
fix: update model directory paths and improve logging in TTS services
2025-01-14 06:37:03 -07:00
remsky
cf72e4ed2b
Add interruptible streams
2025-01-13 23:25:06 -07:00
remsky
064313450e
fix: test of cicd
2025-01-13 20:18:02 -07:00
remsky
22752900e5
Ruff checks, ci fix
2025-01-13 20:15:46 -07:00
remsky
007b1a35e8
feat: merge master into core/uv-management for v0.1.0
...
Major changes:
- Baked model directly into Dockerfile for improved deployment
- Switched to uv for dependency management
- Restructured Docker files into docker/cpu and docker/gpu directories
- Updated configuration for better ONNX performance
2025-01-13 19:31:44 -07:00
remsky
387653050b
refactor: streamline audio normalization process and update tests
2025-01-13 18:56:49 -07:00
remsky
f4dc292440
fix: ui stability, memory safeties
2025-01-12 21:33:23 -07:00
remsky
3d0ca2a8c2
Update Dockerfiles for baked in models, adjustments to cpu/gpu environment splits
2025-01-12 05:23:02 -07:00
remsky
926ea8cecf
Refactor Docker configurations and update test mocks for development routers
2025-01-10 22:03:16 -07:00
remsky
e8c1284032
Ruff format + fix
2025-01-09 18:41:44 -07:00
remsky
4b521f9bf0
- Added GenerateFromPhonemesRequest model to text_schemas.py
...
- Refactored TTS model initialization methods in tts_gpu.py and tts_cpu.py
- Added custom logger configuration in main.py
- Deprecated text_processing router -> development route
2025-01-09 07:20:14 -07:00
remsky
bd4df84410
Merge pull request #12 from fireblade2534/master
...
Gave it a test, didn't see any issues 👍
2025-01-09 01:30:07 -07:00
Fireblade
1f22cda9be
Fix remaining slashes not being converted into text and made % be converted
2025-01-08 08:50:22 -05:00
remsky
a0a85f5ef0
-add email handling, minor additional URL processing, tests
2025-01-08 03:13:17 -07:00
remsky
e7ffcf49f5
fixed: async scandir finding voices
2025-01-07 21:36:07 -07:00
Fireblade
1625082724
Fix url parsing for urls without https, http, or www. It also allows raw ips, ports, and dashs
2025-01-07 19:34:38 -05:00
remsky
d7e8a5c953
Adjusting aiofiles implementation, testing
2025-01-07 04:30:02 -07:00
remsky
130b084cce
- Added support for combining voices via any endpoint
...
- Updated the `process_voices` function to handle both string and list formats for voice input.
2025-01-07 03:50:08 -07:00
remsky
fddf26c905
Added tested, slight changes to regex
2025-01-07 00:18:44 -07:00
Fireblade
db2f3dd323
Made urls readable
2025-01-06 19:40:21 -05:00
remsky
720c1fb97d
-update soundfile version
...
-alignment with streaming standards
-audio processing config settings
-more comprehensive model warmup
-minor model improvements
-enhancing testing, benchmarking
-cool ascii logo
2025-01-06 03:32:41 -07:00
remsky
4c6cd83f85
Swapped generator to preprocessing
2025-01-04 22:23:59 -07:00
remsky
e799f0c7c1
WIP: basic tests on OpenAI streaming compatibility
2025-01-04 18:09:23 -07:00
remsky
0e9f77fc79
WIP: open ai compatible streaming
2025-01-04 17:55:36 -07:00
remsky
f1eb1d9590
First streaming attempt
2025-01-04 17:54:54 -07:00
remsky
93aa205da9
Enhance ONNX optimization settings and add validation script for TTS audio files
2025-01-04 02:14:46 -07:00
remsky
7df2a68fb4
- CPU ONNX + PyTorch CUDA, functional
...
- Incorporated text processing module as service, towards modularization and optimizations
- Added text processing router for phonemization
- Enhanced benchmark statistics with real-time speed metrics
2025-01-03 17:54:17 -07:00
remsky
9496a3a63f
WIP: CPU/GPU Functional, few straggling tests to fix and check.
2025-01-03 03:16:42 -07:00
remsky
e4d8e74738
WIP, Functional for CPU: Updated for ONNX runtime support, Dockerfile and TTS Service
2025-01-03 00:53:41 -07:00
remsky
40894449da
added output audio tests, validation
2025-01-02 15:36:53 -07:00
DINMAY KUMAR BRAHMA
8ccca1fcad
Update audio.py
2025-01-03 00:28:59 +05:30
DINMAY KUMAR BRAHMA
e9014e620e
Merge branch 'remsky:master' into master
2025-01-02 21:37:01 +05:30
remsky
f051984805
Ruff Check + Format
2025-01-01 21:50:41 -07:00
remsky
53cf71c151
-Removed commit lock on HF repo
...
-Warm start added to model initialization
-Layer caching tweaks to dockerfile
2025-01-01 17:38:22 -07:00
DINMAY KUMAR BRAHMA
94b6fc22ea
Update audio.py
2025-01-01 21:11:23 +05:30
remsky
05e1e30c47
- modified voice loading to copy on init
...
- adjustments to the combine voices functionality
- error handling and analysis
2024-12-31 18:55:26 -07:00
Emmanuel Schmidbauer
510b01cc90
add ability to combine voices
2024-12-31 10:30:12 -05:00
remsky
36606f7234
Refactor Docker setup to use a dedicated model-fetcher service and update schemas for additional voice support
2024-12-31 03:41:45 -07:00
remsky
4123ab0891
Refactor TTS API and enhance testing setup with coverage and logging improvements
2024-12-31 02:55:51 -07:00
remsky
c11a6ea6ea
Enhance TTS API with logging, voice pack loading, and schema updates
2024-12-31 01:57:00 -07:00
remsky
8ce8334345
- Complete TTS endpoint replacement with OpenAI compatible
...
-Removed output directory, and update configuration settings
- Added benchmarking for entire novel
2024-12-31 01:52:16 -07:00
remsky
175daea325
Added basic pytest on the fastapi side
2024-12-30 13:25:30 -07:00
